elevation-mcp-server

Get Route Elevation Profile

elevation_get_profile

Read-onlyIdempotent

Sample terrain elevation at evenly spaced points along a route (a polyline of 2–1,000 vertices) and summarize it. Returns total distance, cumulative ascent and descent, start, end, minimum, and maximum elevation, and the steepest climb and descent grades, plus the per-sample profile with each sample's dataset unless include_samples is false. Ascent and descent are summed between samples, so they depend on the sample spacing reported in the result: denser sampling captures more small climbs, down to the source's resolution. Over open water, Mapzen samples are sea-floor depths. Each USGS 3DEP sample is a separate upstream request, so up to 250 samples take roughly 10–30 seconds.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`path`	Yes	Route vertices in travel order, 2–1,000 {lat, lon} objects in decimal degrees (WGS84). Consecutive duplicate vertices are ignored. Antipodal retained segments require an intermediate waypoint, even with endpoint-only sampling; errors identify zero-based submitted vertex indices.
`source`	No	Elevation source: auto (default) uses USGS 3DEP where it has data and Open Topo Data (SRTM, with Mapzen terrain tiles where SRTM has no data) for the rest; usgs_3dep uses 3DEP only; opentopodata uses Open Topo Data only. Case is ignored and spaces or hyphens read as underscores, so USGS-3DEP and open topo data are accepted; 3dep, usgs, and epqs are also aliases for usgs_3dep.	auto
`samples`	No	Number of evenly spaced samples along the route, endpoints included (2–250, default 100). More samples catch more relief and take longer; spacing finer than the source resolution adds no detail. For a large count where only the summary matters, set include_samples to false.
`include_samples`	No	Return the per-sample profile (default true). false omits samples and the sample table; the summary, spacing, coverage counts, datasets, notices, and attribution are unchanged, still computed from every sample.

Output Schema

TableJSON Schema

Name	Required	Description
`error`	No	Present when the call failed. Absent on success.
`notice`	No	Guidance on samples without data, routes crossing the USGS 3DEP coverage edge, Mapzen sea-floor values, and sample spacing against the source resolution.
`samples`	No	Every sample in route order, endpoints included. Absent when include_samples is false.
`summary`	No	Route statistics over the samples with data, bridging samples without data.
`vertices`	No	Route vertices after dropping consecutive duplicates.
`attribution`	No	Sources to credit for the returned values, one line per dataset that answered.
`source_mode`	No	The source the call used (auto unless the caller chose one).
`datasets_used`	No	Number of values each dataset answered.
`missing_samples`	No	Samples no queried dataset answered.
`sample_interval_m`	No	Distance between consecutive samples, meters: route length / (samples − 1).
`samples_with_data`	No	Samples with an elevation.
`resolution_m_range`	No	Range of source resolutions over values that report one; absent when none does (all Mapzen).
`vertical_reference`	No	Height-reference context per answering dataset, including unverified references and whether heights share a datum. No vertical datum conversion is performed.

Schema Changelog

Changes observed during successful MCP inspections.

Changed5 schema fields changedOct 18, 2026

changedInput schema / properties / path / description

Previous value: -"Route vertices in travel order, 2–1,000 {lat, lon} objects in decimal degrees (WGS84). Consecutive duplicate vertices are ignored."New value: +"Route vertices in travel order, 2–1,000 {lat, lon} objects in decimal degrees (WGS84). Consecutive duplicate vertices are ignored. Antipodal retained segments require an intermediate waypoint, even with endpoint-only sampling; errors identify zero-based submitted vertex indices."

changedOutput schema / anyOf

Previous value: -[
-  {
-    "not": {
-      "required": [
-        "error"
-      ]
-    },
-    "required": [
-      "summary",
-      "sample_interval_m",
-      "vertices",
-      "samples_with_data",
-      "missing_samples",
-      "datasets_used",
-      "source_mode",
-      "attribution"
-    ]
-  },
-  {
-    "required": [
-      "error"
-    ]
-  }
-]New value: +[
+  {
+    "not": {
+      "required": [
+        "error"
+      ]
+    },
+    "required": [
+      "summary",
+      "sample_interval_m",
+      "vertices",
+      "samples_with_data",
+      "missing_samples",
+      "datasets_used",
+      "source_mode",
+      "vertical_reference",
+      "attribution"
+    ]
+  },
+  {
+    "required": [
+      "error"
+    ]
+  }
+]

changedOutput schema / properties / error / properties / data / properties / reason / description

Previous value: -"Machine-readable failure mode. Declared by this tool: `degenerate_path`: After dropping consecutive duplicate vertices, fewer than 2 vertices remain, or the route is under 1 m long. `no_coverage`: No sample along the route returned an elevation. `usgs_unavailable`: USGS 3DEP failed: a server error, rate limit, network error, or timeout that outlasted the retries (retryable), or a client error or unexpected status that retrying cannot fix (not retryable). `opentopodata_unavailable`: Open Topo Data failed: a server error, network error, timeout, or unreadable response that outlasted the retries (retryable), or an unexpected status that retrying cannot fix (not retryable). `opentopodata_rate_limited`: Open Topo Data kept answering HTTP 429 through the retries, or asked for a wait over 8 s. `opentopodata_daily_limit`: Only on the public Open Topo Data instance: this server has sent it 1,000 requests in the trailing 24 hours, so no request was sent. `opentopodata_config_rejected`: The Open Topo Data instance answered 401, 403, or 404, a redirect from a self-hosted instance, a 400 naming a dataset it lacks or a location limit below 100, or a 200 naming a dataset this server did not request. `sampling_deadline_exceeded`: The call's 45 s sampling budget ran out (a retry deadline, or a wait in either provider's request queue), or the USGS 3DEP lookups other calls had queued, plus this call's, would not drain within the calls' budgets, so it sent none and data.retryAfter gives the seconds until the queued lookups drain. Other values are possible when a failure originates below the handler."New value: +"Machine-readable failure mode. Declared by this tool: `antipodal_path`: A retained path segment has antipodal endpoints after dropping consecutive duplicates, so its shorter arc is ambiguous. `degenerate_path`: After dropping consecutive duplicate vertices, fewer than 2 vertices remain, or the route is under 1 m long. `no_coverage`: No sample along the route returned an elevation. `usgs_unavailable`: USGS 3DEP failed: a server error, rate limit, network error, or timeout that outlasted the retries (retryable), or a client error or unexpected status that retrying cannot fix (not retryable). `opentopodata_unavailable`: Open Topo Data failed: a server error, network error, timeout, or unreadable response that outlasted the retries (retryable), or an unexpected status that retrying cannot fix (not retryable). `opentopodata_rate_limited`: Open Topo Data kept answering HTTP 429 through the retries, or asked for a wait over 8 s. `opentopodata_daily_limit`: Only on the public Open Topo Data instance: this server has sent it 1,000 requests in the trailing 24 hours, so no request was sent. `opentopodata_config_rejected`: The Open Topo Data instance answered 401, 403, or 404, a redirect from a self-hosted instance, a 400 naming a dataset it lacks or a location limit below 100, or a 200 naming a dataset this server did not request. `sampling_deadline_exceeded`: The call's 45 s sampling budget ran out (a retry deadline, or a wait in either provider's request queue), or the USGS 3DEP lookups other calls had queued, plus this call's, would not drain within the calls' budgets, so it sent none and data.retryAfter gives the seconds until the queued lookups drain. Other values are possible when a failure originates below the handler."

changedOutput schema / properties / error / properties / data / properties / reason / examples

Previous value: -[
-  "degenerate_path",
-  "no_coverage",
-  "usgs_unavailable",
-  "opentopodata_unavailable",
-  "opentopodata_rate_limited",
-  "opentopodata_daily_limit",
-  "opentopodata_config_rejected",
-  "sampling_deadline_exceeded"
-]New value: +[
+  "antipodal_path",
+  "degenerate_path",
+  "no_coverage",
+  "usgs_unavailable",
+  "opentopodata_unavailable",
+  "opentopodata_rate_limited",
+  "opentopodata_daily_limit",
+  "opentopodata_config_rejected",
+  "sampling_deadline_exceeded"
+]

addedOutput schema / properties / vertical_reference

Added value: +{
+  "description": "Height-reference context per answering dataset, including unverified references and whether heights share a datum. No vertical datum conversion is performed.",
+  "type": "string"
+}

First observedOct 2, 2026

TDQS

A4.6/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the readOnly/idempotent/openWorld annotations, it discloses non-obvious behavior: ascent/descent depend on sample spacing because they are summed between samples, Mapzen returns sea-floor depths over open water, and each USGS 3DEP sample is a separate upstream request costing roughly 10–30 seconds for up to 250 samples. These are exactly the traits an agent cannot derive from annotations or schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The opening sentence front-loads purpose and return contents, then caveats follow in descending priority. It is dense and runs long, but every sentence carries distinct information (spacing dependency, water depths, per-sample request cost) rather than filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, the description needn't enumerate return fields, yet it usefully summarizes them; annotations cover safety, and the description fills the remaining gaps — sampling tradeoffs, data-source semantics, and latency expectations — so an agent has everything needed to call this correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds cross-parameter semantics the schema does not: the dependency of ascent/descent totals on the samples spacing reported in the result, and the tradeoff that denser sampling catches more relief at higher latency. It reinforces rather than duplicates the schema's per-field text.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource — sample terrain elevation at evenly spaced points along a route polyline and summarize it — and immediately scopes it with the 2–1,000 vertex constraint. This is clearly distinguishable from siblings like elevation_get_points (discrete points), elevation_get_grid (area grid), and elevation_check_line_of_sight (visibility).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives clear operating context: use include_samples=false when only the summary matters for a large sample count, and that spacing finer than source resolution adds no detail. However, it never names a sibling or states when to prefer elevation_get_points or elevation_get_grid over this tool, so selection among siblings is left to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All elevation-mcp-server tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.